相关论文: On the Foundations of Trustworthy Artificial Intel…

Modern AI systems are reaping the advantage of novel learning methods. With their increasing usage, we are realizing the limitations and shortfalls of these systems. Brittleness to minor adversarial changes in the input data, ability to…

We present CAIA, a benchmark exposing a critical blind spot in AI evaluation: the inability of state-of-the-art models to operate in adversarial, high-stakes environments where misinformation is weaponized and errors are irreversible. While…

Manufacturing lines, service journeys, supply chains, and AI reasoning chains share a common challenge: attributing a terminal outcome to the intermediate stage that caused it. We establish an information-theoretic barrier to this credit…

As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), is increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core…

How can we assess the reliability of a dataset without access to ground truth? We introduce the problem of reliability scoring for datasets collected from potentially strategic sources. The true data are unobserved, but we see outcomes of…

In recent years, machine learning (ML) and neural networks (NNs) have gained widespread use and attention across various domains, particularly in transportation for achieving autonomy, including the emergence of flying taxis for urban air…

An edge computing marketplace could enable IoT devices (Outsourcers) to outsource computation to any participating node (Contractors) in their proximity. In return, these nodes receive a reward for providing computation resources. In this…

The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the complex interplay between privacy, verifiability, and…

In collaborative systems with complex tasks relying on distributed resources, trust evaluation of potential collaborators has emerged as an effective mechanism for task completion. However, due to the network dynamics and varying…

Edge Intelligence (EI) integrates Edge Computing (EC) and Artificial Intelligence (AI) to push the capabilities of AI to the network edge for real-time, efficient and secure intelligent decision-making and computation. However, EI faces…

Explainability and Safety engender Trust. These require a model to exhibit consistency and reliability. To achieve these, it is necessary to use and analyze data and knowledge with statistical and symbolic AI methods relevant to the AI…

Modern cloud-based AI training relies on extensive telemetry and logs to ensure accountability. While these audit trails enable retrospective inspection, they struggle to address the inherent non-determinism of deep learning. Stochastic…

We demonstrate sufficiency of events-based synchronisation for solving deterministic fault-tolerant consensus in asynchrony. Main result is an algorithm that terminates with valid vector agreement, hence operates with safety, liveness, and…

Process attestation systems verify that a continuous physical process, such as human authorship, actually occurred, rather than merely checking system state. These systems face a fundamental dependability challenge: the evidence collection…

Ensuring responsible use of artificial intelligence (AI) has become imperative as autonomous systems increasingly influence critical societal domains. However, the concept of trustworthy AI remains broad and multi-faceted. This thesis…

A current concern in the field of Artificial Intelligence (AI) is to ensure the trustworthiness of AI systems. The development of explainability methods is one prominent way to address this, which has often resulted in the assumption that…

With edge-AI finding an increasing number of real-world applications, especially in industry, the question of functionally safe applications using AI has begun to be asked. In this body of work, we explore the issue of achieving dependable…

AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic…

The rapid integration of artificial intelligence (AI) into Internet of Things (IoT) and edge computing systems has intensified the need for robust, hardware-rooted trust mechanisms capable of ensuring device authenticity and AI model…

We formalize AI alignment as a multi-objective optimization problem called $\langle M,N,\varepsilon,\delta\rangle$-agreement, in which a set of $N$ agents (including humans) must reach approximate ($\varepsilon$) agreement across $M$…